Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    polynomial reduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entino
    -0.09
    共同
    -0.08
    締
    -0.08
     арас
    -0.08
     саны
    -0.08
     کشورهای
    -0.08
     international
    -0.08
    Separator
    -0.07
    拥
    -0.07
    Caption
    -0.07
    POSITIVE LOGITS
     derivatives
    0.09
     Reduce
    0.09
     ores
    0.08
     fraî
    0.08
     Substitute
    0.08
     terug
    0.08
     recursively
    0.08
     �
    0.08
     alde
    0.08
     simplify
    0.08
    Act Density 0.018%

    No Known Activations